Search

One of the ways of achieving improved capacity in mobile cellular networks is via network densification. Even though densification increases the capacity of the network, it also leads to increased energy consumption which can be curbed by dynamically switching off some base stations (BSs) during periods of low traffic. However, dynamic cell switching has the challenge of spectrum under-utilizationas the spectrum originally occupied by the BSs that are turned off remains dormant. This dormant spectrum can be leased by the primary network (PN) operators, who hold the license, to the secondary network (SN) operators who cannot afford to purchase the spectrum license. Thus enabling the PN to gain additional revenue from spectrum leasing as well as from electricity cost savings due to reduced energy consumption. Therefore, in this work, we propose a cell switching and spectrum leasing framework based on simulated annealing (SA) algorithm to maximize the revenue of the PN while respecting the quality-of-service constraints. The performance evaluation reveals that the proposed method is very close to optimal exhaustive search method with a significant reduction in the computation complexity., Comment: 28 pages, 6 figures, Submitted to IEEE Transactions on cognitive communications and networking (TCCN)

The next generation mobile networks (NGMNs) are envisioned to overcome current user mobility limitations while improving the network performance. Some of the limitations envisioned for mobility management in the future mobile networks are: addressing the massive traffic growth bottlenecks; providing better quality and experience to end users; supporting ultra high data rates; ensuring ultra low latency, seamless handover (HOs) from one base station (BS) to another, etc. Thus, in order for future networks to manage users mobility through all of the stringent limitations mentioned, artificial intelligence (AI) is deemed to play a key role automating end-to-end process through machine learning (ML). The objectives of this thesis are to explore user mobility predictions and management use-cases using ML. First, background and literature review is presented which covers, current mobile networks overview, and ML-driven applications to enable user’s mobility and management. Followed by the use-cases of mobility prediction in dense mobile networks are analysed and optimised with the use of ML algorithms. The overall framework test accuracy of 91.17% was obtained in comparison to all other mobility prediction algorithms through artificial neural network (ANN). Furthermore, a concept of mobility prediction-based energy consumption is discussed to automate and classify user’s mobility and reduce carbon emissions under smart city transportation achieving 98.82% with k-nearest neighbour (KNN) classifier as an optimal result along with 31.83% energy savings gain. Finally, context-aware handover (HO) skipping scenario is analysed in order to improve over all quality of service (QoS) as a framework of mobility management in next generation networks (NGNs). The framework relies on passenger mobility, trains trajectory, travelling time and frequency, network load and signal ratio data in cardinal directions i.e, North, East, West, and South (NEWS) achieving optimum result of 94.51% t

The next generation mobile networks (NGMNs) are envisioned to overcome current user mobility limitations while improving the network performance. Some of the limitations envisioned for mobility management in the future mobile networks are: addressing the massive traffic growth bottlenecks; providing better quality and experience to end users; supporting ultra high data rates; ensuring ultra low latency, seamless handover (HOs) from one base station (BS) to another, etc. Thus, in order for future networks to manage users mobility through all of the stringent limitations mentioned, artificial intelligence (AI) is deemed to play a key role automating end-to-end process through machine learning (ML). The objectives of this thesis are to explore user mobility predictions and management use-cases using ML. First, background and literature review is presented which covers, current mobile networks overview, and ML-driven applications to enable user’s mobility and management. Followed by the use-cases of mobility prediction in dense mobile networks are analysed and optimised with the use of ML algorithms. The overall framework test accuracy of 91.17% was obtained in comparison to all other mobility prediction algorithms through artificial neural network (ANN). Furthermore, a concept of mobility prediction-based energy consumption is discussed to automate and classify user’s mobility and reduce carbon emissions under smart city transportation achieving 98.82% with k-nearest neighbour (KNN) classifier as an optimal result along with 31.83% energy savings gain. Finally, context-aware handover (HO) skipping scenario is analysed in order to improve over all quality of service (QoS) as a framework of mobility management in next generation networks (NGNs). The framework relies on passenger mobility, trains trajectory, travelling time and frequency, network load and signal ratio data in cardinal directions i.e, North, East, West, and South (NEWS) achieving optimum result of 94.51% t